Search Results for "format"

MarkItDown is a lightweight Python utility developed by Microsoft for converting various files and office documents to Markdown format. It is particularly useful for preparing documents for use with large language models and related text analysis pipelines. ​

Shrimp Task Manager is an MCP server that converts natural-language requests into structured development tasks with dependencies, status, and style/format rules—built for agents that reason step-by-step. It emphasizes chain-of-thought and reflection loops, allowing an assistant to plan, refine, and re-prioritize work like a human project assistant. The server exposes typed tools so clients can create tasks, link prerequisites, record progress, and enforce writing or coding standards for consistent output. ...

The MCP Notion Server is an MCP server implementation that integrates with Notion, allowing AI assistants to interact with and manage Notion content. It facilitates seamless access to Notion's databases and pages. ​

...The project offers two execution paths—run the compiled app or run from source—and documents default download and configuration paths to simplify first use. Recent releases add format support like JPEG and HEIC, clipboard-listening mode improvements, author-based archiving, SOCKS/HTTP proxy options, and the ability to set the file’s modification time to the post’s publish time for cleaner library organization. There is an active issues/discussions area with community tips, including approaches that use Selenium to acquire cookies and user agents for more reliable downloads.

The MCP Server Giphy is a Model Context Protocol (MCP) server that enables AI models to search, retrieve, and utilize GIFs from the Giphy platform. It facilitates seamless integration of Giphy's vast GIF library into AI applications, enhancing their expressive capabilities. ​

...The tool targets analysts who need one-click collection and normalized output to reduce manual lookups across registries and platforms. Recent releases added a reworked task model with queueing, resumable searches via cached progress, export format options, and a public API surface for custom keyword strategies. Documentation and issues discuss operational concerns such as rate limits, verification challenges, and use of proxies to reduce bans. The project is maintained under Apache-2.0 and is positioned for both single-shot queries and batch investigations.

...Nerve is a simple yet powerful Agent Development Kit (ADK) to build, run, evaluate, and orchestrate LLM-based agents using just YAML and a CLI. It’s designed for technical users who want programmable, auditable, and reproducible automation using large language models. Define agents using a clean YAML format: system prompt, task, tools, and variables — all in one file.

...From any supported identifier - DOI, PMID, PMCID, ISBN, arXiv ID, ISSN, NASA ADS bibcode, or WHO IRIS URL - it can: - resolveIdentifier - return structured bibliographic metadata (CSL JSON) - formatCitation - format into 10,000+ CSL styles (Vancouver, APA, AMA, IEEE, CSE, or any CSL style ID) - exportCitation - export to BibTeX, RIS, CSL JSON, EndNote, RefWorks, MEDLINE, Zotero RDF, CSV, or plain text - checkRetraction - surface retractions, corrections, and expressions of concern (Crossref / Retraction Watch) - checkOpenAccess - report OA status and the best legal landing/PDF URL (Unpaywall) - verifyCitation - cross-check a claimed citation against the record at its identifier, detecting the AI-driven "real DOI + invented title" fabrication pattern that simple resolution cannot catch MIT licensed; source on GitHub.